plugins/github-copilot-modernization/skills/implementing-code/SKILL.md
Executes a batch of implementation tasks with TDD workflow, source-anchored rewrite for behavioral fidelity, guideline-based code transformation, and full requirement tracing. Returns a structured batch report. Triggers: "implement tasks", "execute the batch", "write code for these tasks", "implement with source anchoring", "run the implementation". NOT for: task generation (use breaking-down-tasks), implementation planning (use creating-implementation-plan).
npx skillsauth add microsoft/github-copilot-modernization implementing-codeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You MUST consider the user input before proceeding (if not empty).
Code files are written into the project tree. The batch report is written under the provided artifact path.
batch-report.yaml ← structured result consumed by caller
Confirm required artifacts exist: plan.md (with task list and Requirement Mapping table), feature spec.
Read from the provided artifact path and dependency artifacts. Scan the artifact directory to find these categories:
| Category | Required | Purpose | Look for |
|----------|----------|---------|----------|
| Task breakdown | ✅ | Work items with T-IDs to implement | Artifact with task IDs (T001, T002...), may be in tasks/ subdirectory or main planning artifact |
| Feature spec | ✅ | Requirements (REQ-XXX) and acceptance criteria | Artifact with REQ-XXX identifiers and user scenarios |
| Constitution | ✅ | Project principles and constraints | Usually named constitution.md in artifact root |
| Implementation plan | ✅ | Phased plan with architecture decisions | Artifact with phased sections and plan references |
| Architecture design | ✅ | API contracts, layering, package structure | Artifact with design decisions |
| Data model | If exists | Entity definitions, mappings, FK strategy | Artifact with schema/entity details |
| UX/UI spec | If exists | Screen layouts, user flows, components | Artifact with screen specs |
| Knowledge graph | If exists | Module dependencies and class relationships | JSON file with nodes/edges in artifact path |
| Checkpoints | If exists | Upstream traceability | YAML files in checkpoints/ subdirectory |
| Guidelines | If exists | Migration rules and transformation patterns | Search guidelines skill |
If checklists/ directory exists, scan checklist files. If any incomplete items: display table and ask before proceeding.
Create/verify ignore files. See references/ignore-patterns.md for patterns by language/tool.
From the task breakdown artifact, find tasks that match your current assignment:
Unmet dependency not in current batch → report as blocked.
Ordering:
[P] tasks: can run togetherTDD Flow:
mvn test -pl <module> -am). ALL tests must PASS. Report pass/fail/skip counts in batch report. Test failure = task NOT complete.Constitution & Requirement Fidelity:
REQ-XXX — implement requirement intent, not just task description.Source-Anchored Rewrite (MANDATORY in rewrite mode):
For tasks with [Source:], follow references/source-anchored-rewrite.md.
Guideline-Based Transformation:
For tasks marked [GUIDELINE:skill-name]:
skills/guidelines/Parallelism: Run independent tasks ([P] marked) in parallel as much as possible to maximize throughput.
Error Handling:
[P] tasks: continue successful ones, report failuresAfter ALL tasks in this batch complete, write checkpoints/tasks-to-impl.yaml using templates/tasks-to-impl-checkpoint-template.yaml. This is REQUIRED — completeness gate reads it to verify traceability.
Generate batch result report per references/batch-report-format.md (YAML format).
references/source-anchored-rewrite.md — Rewrite-mode behavioral fidelity processreferences/ignore-patterns.md — Ignore file patterns by language/toolreferences/batch-report-format.md — Required YAML output formatdevelopment
Evaluates whether a user's modernization/rewrite request provides enough scenario context to proceed (e.g., target component library, screenshots, design system for frontend; API contract policy, data migration strategy for backend). Produces a deterministic clarity score, asks the user for missing required fields via a structured form, and writes a canonical `clarification.md` artifact consumed by all downstream agents. Triggers: "clarification gate", "scenario clarification", "elicit missing context", "evaluate prompt completeness", "ask user for screenshots / target library / design system". NOT for: feature specification (use feature-inventory), planning (use creating-implementation-plan), implementation (use implementing-code), or resolving spec-time `[NEEDS CLARIFICATION]` markers (those remain owned by feature-inventory).
tools
Lifecycle hooks for the modernize-rearchitecture coordinator. Defines hook points, registered actions, and execution rules.
development
Provides role charters (mission, ownership, core principles, quality bar) for a multi-agent coding team. Each charter defines the role's mission, ownership scope, core principle (boundary constraints), and quality bar. Most roles also include communication rules. Consumed by the coordinator during task decomposition to assign work to the correct role. Triggers: "look up role charter", "what does the architect own", "check role boundaries", "find team roles", "which role handles X", "list agent charters", "role responsibilities". NOT for: task decomposition (use breaking-down-tasks), implementation (use implementing-code), architecture analysis (use analyzing-architecture).
tools
Zero-dependency shell recon for any code repository — detect languages, count LOC, and report project scale. Pure POSIX find/wc or PowerShell, no Python or third-party tools required. Triggers: "how big is this project", "what languages", "project sizing", "repo recon", "LOC count", "scope check".